Read Training AI to Diagnose Mental Illness»

R
B David Zarley at The Verge:

Chiu is acutely aware of what’s at stake: if the diagnostic and custom treatment guidelines her lab’s algorithms discover are infected with the same human biases already at work in society, they will simply codify — and perhaps even strengthen — those biases... Further complicating matters is the lack of ground truth in psychiatric data sets, a human-vetted training set with which we can test the machine’s learning. A machine learning algorithm, which diagnoses, say, skin cancer, has a training set of samples which have been biopsied and cataloged, leaving no doubt as to whether they are malignant or not. But there is no biopsy for mental health disorders, at least not yet.

An intriguing article by B David Zarley at The Verge about using machine learning to potentially diagnose mental illness. Interesting to note those challenges common to machine learning and those unique to mental health diagnosis and the interaction between them.
By Andrew Ford

About Normality

Normality is a personal experiment in social networking using open standards such as micro-blog and webmentions to enable interaction while retaining control of content.

Normality is solely authored by Andrew Ford as a platform for personal expression and interpersonal discussion.

Andrew Ford

Andrew is passionately opinionated about all things technology, is a proud new father to a beautiful son and currently is occupied, earning his keep as a Registered Nurse in the majestic country of New Zealand.

Follow Me